Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology
Deformable objects such as ropes, wires, and clothing are omnipresent in society and industry but are little researched in robotics research. This is due to the infinite amount of possible state configurations caused by the deformations of the deformable object. Engineered approaches try to cope wit...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/12/4088 |
id |
doaj-6e4f04e4a300436495c74fc3b8461853 |
---|---|
record_format |
Article |
spelling |
doaj-6e4f04e4a300436495c74fc3b84618532020-11-25T03:17:07ZengMDPI AGApplied Sciences2076-34172020-06-01104088408810.3390/app10124088Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile TechnologyAndreas Verleysen0Thomas Holvoet1Remko Proesmans2Cedric Den Haese3Francis wyffels4IDLab-AIRO, Electronics and Information Systems Department, Ghent University, 9052 Zwijnaarde, BelgiumIDLab-AIRO, Electronics and Information Systems Department, Ghent University, 9052 Zwijnaarde, BelgiumIDLab-AIRO, Electronics and Information Systems Department, Ghent University, 9052 Zwijnaarde, BelgiumIDLab-AIRO, Electronics and Information Systems Department, Ghent University, 9052 Zwijnaarde, BelgiumIDLab-AIRO, Electronics and Information Systems Department, Ghent University, 9052 Zwijnaarde, BelgiumDeformable objects such as ropes, wires, and clothing are omnipresent in society and industry but are little researched in robotics research. This is due to the infinite amount of possible state configurations caused by the deformations of the deformable object. Engineered approaches try to cope with this by implementing highly complex operations in order to estimate the state of the deformable object. This complexity can be circumvented by utilizing learning-based approaches, such as reinforcement learning, which can deal with the intrinsic high-dimensional state space of deformable objects. However, the reward function in reinforcement learning needs to measure the state configuration of the highly deformable object. Vision-based reward functions are difficult to implement, given the high dimensionality of the state and complex dynamic behavior. In this work, we propose the consideration of concepts beyond vision and incorporate other modalities which can be extracted from deformable objects. By integrating tactile sensor cells into a textile piece, proprioceptive capabilities are gained that are valuable as they provide a reward function to a reinforcement learning agent. We demonstrate on a low-cost dual robotic arm setup that a physical agent can learn on a single CPU core to fold a rectangular patch of textile in the real world based on a learned reward function from tactile information.https://www.mdpi.com/2076-3417/10/12/4088deformable object manipulationsmart textilelow-costreinforcement learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Andreas Verleysen Thomas Holvoet Remko Proesmans Cedric Den Haese Francis wyffels |
spellingShingle |
Andreas Verleysen Thomas Holvoet Remko Proesmans Cedric Den Haese Francis wyffels Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology Applied Sciences deformable object manipulation smart textile low-cost reinforcement learning |
author_facet |
Andreas Verleysen Thomas Holvoet Remko Proesmans Cedric Den Haese Francis wyffels |
author_sort |
Andreas Verleysen |
title |
Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology |
title_short |
Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology |
title_full |
Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology |
title_fullStr |
Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology |
title_full_unstemmed |
Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology |
title_sort |
simpler learning of robotic manipulation of clothing by utilizing diy smart textile technology |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-06-01 |
description |
Deformable objects such as ropes, wires, and clothing are omnipresent in society and industry but are little researched in robotics research. This is due to the infinite amount of possible state configurations caused by the deformations of the deformable object. Engineered approaches try to cope with this by implementing highly complex operations in order to estimate the state of the deformable object. This complexity can be circumvented by utilizing learning-based approaches, such as reinforcement learning, which can deal with the intrinsic high-dimensional state space of deformable objects. However, the reward function in reinforcement learning needs to measure the state configuration of the highly deformable object. Vision-based reward functions are difficult to implement, given the high dimensionality of the state and complex dynamic behavior. In this work, we propose the consideration of concepts beyond vision and incorporate other modalities which can be extracted from deformable objects. By integrating tactile sensor cells into a textile piece, proprioceptive capabilities are gained that are valuable as they provide a reward function to a reinforcement learning agent. We demonstrate on a low-cost dual robotic arm setup that a physical agent can learn on a single CPU core to fold a rectangular patch of textile in the real world based on a learned reward function from tactile information. |
topic |
deformable object manipulation smart textile low-cost reinforcement learning |
url |
https://www.mdpi.com/2076-3417/10/12/4088 |
work_keys_str_mv |
AT andreasverleysen simplerlearningofroboticmanipulationofclothingbyutilizingdiysmarttextiletechnology AT thomasholvoet simplerlearningofroboticmanipulationofclothingbyutilizingdiysmarttextiletechnology AT remkoproesmans simplerlearningofroboticmanipulationofclothingbyutilizingdiysmarttextiletechnology AT cedricdenhaese simplerlearningofroboticmanipulationofclothingbyutilizingdiysmarttextiletechnology AT franciswyffels simplerlearningofroboticmanipulationofclothingbyutilizingdiysmarttextiletechnology |
_version_ |
1724633230208925696 |